7 papers
DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption
Chang Liu, Yuni Lai, Mingyue Cui +5
Multimodal Retrieval Augmented Generation (M-RAG) is increasingly vulnerable to adversarial attacks where malicious data are crafted to produce embeddings that align with benign en…
Stealthy Dual-Trigger Backdoors: Attacking Prompt Tuning in LM-Empowered Graph Foundation Models
Xiaoyu Xue, Yuni Lai, Chenxi Huang +4
The emergence of graph foundation models (GFMs), particularly those incorporating language models (LMs), has revolutionized graph learning and demonstrated remarkable performance o…
Provably Robust Adaptation for Language-Empowered Foundation Models
Yuni Lai, Xiaoyu Xue, Linghui Shen +5
Language-empowered foundation models (LeFMs), such as CLIP and GraphCLIP, have transformed multimodal learning by aligning visual (or graph) features with textual representations,…
AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional Smoothing
Yuni Lai, Yulin Zhu, Yixuan Sun +6
Despite advancements in Graph Neural Networks (GNNs), adaptive attacks continue to challenge their robustness. Certified robustness via randomized smoothing offers provable guarant…
SFR-GNN: Simple and Fast Robust GNNs against Structural Attacks
Xing Ai, Guanyu Zhu, Yulin Zhu +4
Graph Neural Networks (GNNs) have demonstrated commendable performance for graph-structured data. Yet, GNNs are often vulnerable to adversarial structural attacks as embedding gene…
Spikewhisper: Temporal Spike Backdoor Attacks on Federated Neuromorphic Learning over Low-power Devices
Hanqing Fu, Gaolei Li, Jun Wu +4
Federated neuromorphic learning (FedNL) leverages event-driven spiking neural networks and federated learning frameworks to effectively execute intelligent analysis tasks over amou…
Towards Robust Graph Structural Learning Beyond Homophily via Preserving Neighbor Similarity
Yulin Zhu, Yuni Lai, Xing Ai +7
Despite the tremendous success of graph-based learning systems in handling structural data, it has been widely investigated that they are fragile to adversarial attacks on homophil…